Data-Driven Fault Diagnosis: A Machine Learning Approach for Industrial Components

by Govind Vashishtha

Overview

Data-Driven Fault Diagnosis delves into the application of machine learning techniques for achieving robust and efficient fault diagnosis in industrial components.

The book covers a range of key topics, including data acquisition and preprocessing, feature engineering, model selection and training, and real-time implementation of diagnostic systems. It examines popular machine learning algorithms like Support Vector Machines, Convolutional Neural Network, and Extreme Learning Machine, highlighting their strengths and limitations in different industrial contexts. Practical case studies and real-world examples from various sectors like manufacturing, energy, and transportation illustrate the real-world impact of these techniques.

The aim of this book is to empower engineers, data scientists, and researchers with the knowledge and tools necessary to implement data-driven fault diagnosis systems in their respective industrial domains.

Product Details

ISBN-13:	9781041011637
Publisher:	CRC Press
Publication date:	09/23/2025
Pages:	192
Product dimensions:	6.00(w) x 9.00(h) x (d)

About the Author

Govind Vashishtha received a PhD degree in Mechanical Engineering from the Sant Longowal Institute of Engineering and Technology, Longowal, India, in 2022. He is currently working as a Visiting Professor at Wroclaw University of Science and Technology, Wroclaw, Poland. He has authored over 70 research papers in Science Citation Index (SCI) journals and also edited one book. His name also appeared in the world's top 2% scientist list published by Stanford University in 2023 and 2024. He is also serving as Associate Editor in Frontiers in Mechanical Engineering, Shock and Vibration, Measurement and Engineering and Applications of Artificial Intelligence. He has two Indian patents. His H-index is 27 and has been cited in more than 1700 citations. His current research includes fault diagnosis of mechanical components, vibration and acoustic signal processing, identification/measurement, defect prognosis, machine learning and artificial intelligence.

Table of Contents

1. Introduction.  2. Fault diagnosis of the Pelton turbine.  3.  Fault diagnosis of the Francis turbine.  4. Fault diagnosis of the Centrifugal pump.  5. Fault diagnosis of bearing.  6. The future of machine learning in fault diagnosis.  7. References